© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8606
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to courtroom trials, negative sentiment, and political campaigns.

    oai_token-act-pair · gemini-2.0-flash

    Political commentary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahal
    -0.57
    "}";
    -0.55
     suitcases
    -0.52
    "]));
    -0.51
     ganglia
    -0.51
    AddTagHelper
    -0.50
    esgue
    -0.47
     Baillargeon
    -0.47
    "}"
    -0.47
    ГЛА
    -0.47
    POSITIVE LOGITS
     r
    0.76
     mus
    0.58
     ModelExpression
    0.56
     insuffisamment
    0.54
    WebElementEntity
    0.53
    TintMode
    0.53
    piram
    0.53
     AppCompatTheme
    0.51
     di
    0.50
     Raya
    0.50
    Activations Density 6.260%

    No Known Activations